viz

viz is a command for Claude Code from JSungMin/vs-token-safer. It costs 57 tokens per session (414 once invoked), scanned A, original, MIT.

A local dashboard for viewing token savings, language usage, tool-by-tool savings, and relationships between included files. It opens in a browser and keeps its data on your machine.

In plain words
What is it for?
Use it to explore savings and the file include graph, then warm up the graph or keep using search tools if it has no data yet.
Why use it?
It gives you a visual way to inspect how the token-saving tool is being used without sending dashboard data elsewhere.

Command for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vs-token-safer plugin — 3 skills, 6 commands, 1 agent, 1 MCP server, 1 plugin shipped together

Good fit Use it to explore savings and the file include graph, then warm up the graph or keep using search tools if it has no data yet.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add JSungMin/vs-token-safer
Claude Code
/plugin install vs-token-safer

Made for: Claude Code.

Or install vs-token-safer, the plugin that ships this one along with the rest of its 3 skills, 6 commands, 1 agent, 1 MCP server, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for viz

README.md
[![agentmods](https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/viz.svg)](https://agentmods.dev/commands/jsungmin/vs-token-safer/viz)
Your own site
<a href="https://agentmods.dev/commands/jsungmin/vs-token-safer/viz"><img src="https://agentmods.dev/badge/commands/jsungmin/vs-token-safer/viz.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 414 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00414
Opus 5 $0.00028 $0.00207
Sonnet 5 $0.00011 $0.00083
Haiku 4.5 $0.00006 $0.00041

Measured 7d ago against content hash 8be46b2825c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

viz scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/viz.md · 31 lines

What it actually says

vs-token-safer — open the dashboard

Start the local dashboard server and open it in the browser. It is local-only (binds 127.0.0.1, serves a fully self-contained page + the locally-vendored Three.js — nothing leaves the machine) and opt-in (it is NOT the always-on MCP server; it runs only while this command's process is alive).

Do this:

  1. Run the dashboard in the background (it's a long-running server), opening the browser automatically:

    vts serve --open --projectPath "<the current project root>"
    

    If vts is not on PATH, run the bundled CLI instead:

    node "$CLAUDE_PLUGIN_ROOT/server/cli.js" serve --open --projectPath "<the current project root>"
    

    Launch it with run_in_background: true so it keeps serving across turns. Pass --port <N> if 8731 is taken (the error message says so).

  2. Tell the user the URL it printed (e.g. http://127.0.0.1:8731/) and that it's local-only.

  3. If the include-graph panel is empty, note that the graph fills in after some searches — they can run vts warmup --projectPath <root> --backend <clangd|typescript|…> or just keep using the search/nav tools (each search records into the warm-set + include-graph).

To close it later, use /vs-token-safer:viz-stop (or vts serve --stop, or Ctrl-C the process).

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 31 lines · 57 tokens per session scan A 8be46b2825c1

Subscribe to this mod's changes

viz is a command published in the GitHub repository JSungMin/vs-token-safer (11 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 414 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.